Federated Learning for Cooperative Inference Systems: The Case of Early Exit Networks

arXiv:2405.04249v1 Announce Type: new
Abstract: As Internet of Things (IoT) technology advances, end devices like sensors and smartphones are progressively equipped with AI models tailored to their local memory and computational constraints. Local inference reduces communication costs and latency; however, these smaller models typically underperform compared to more sophisticated models deployed on edge servers or in the cloud. Cooperative Inference Systems (CISs) address this performance trade-off by enabling smaller devices to offload part of their inference tasks to more capable …

abstract advances ai models arxiv case communication computational constraints costs cs.ai cs.dc cs.lg devices exit federated learning however inference internet internet of things iot latency memory networks sensors smartphones systems technology type